awq-quantization

21.8k

davila7

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

skills-manager

451

anyproto

Context-aware routing to skills and hooks management. Use when troubleshooting skill activation, fine-tuning keywords, or managing the automated documentation system.

skill-developer

4

DojoCodingLabs

Create and manage Claude Code skills with auto-activation, progressive disclosure, and memory patterns. Use when creating skills, modifying skill-rules.json, understanding triggers (keywords, intent, file, content), working with hooks (UserPromptSubmit, PreToolUse, Stop), debugging activation, implementing guardrails, or building memory-aware skills that persist context across sessions. Covers 500-line rule, session tracking, enforcement levels (block, suggest, warn), plan-approval workflows, and best practices.